EECS Publication
Energy-aware scheduling under reliability and makespan constraints
Guillaume Aupy, Anne Benoit, Yves Robert
We consider a task graph to be executed on a set of homogeneous processors. We aim at minimizing the energy consumption while enforcing two constraints: a prescribed bound on the execution time (or makespan), and a reliability threshold. Dynamic voltage and frequency scaling (DVFS) is a model frequently used to reduce the energy consumption of a schedule, but it has negative effect on its reliability. In this work, to improve the reliability of a schedule while reducing the energy consumption, we allow for the re-execution of some tasks. We assess the complexity of the tri-criteria scheduling problem (makespan, reliability, energy) with two different speed models: either processors can have arbitrary speeds (continuous speeds), or a processor can run at a finite number of different speeds,and it can change its speed during a computation. We propose several novel tri-criteria scheduling heuristics under the continuous speed model, and we evaluate them through a set of simulations. Our two best heuristics turn out to be very efficient and complementary
Published 2011-10-25 04:00:00 as ut-cs-11-686 (ID:48)